proctor for VS Code

io.github.louissarvin/proctor

Human oversight for AI agents: block a tool call on a verified human, with on-chain proof.

client:VS Code transport:stdio runtime:npm

Install proctor in VS Code

.vscode/mcp.json

{
  "inputs": [
    {
      "type": "promptString",
      "id": "proctor-api",
      "description": "PROCTOR_API",
      "password": true
    },
    {
      "type": "promptString",
      "id": "hedera-agent-id",
      "description": "HEDERA_AGENT_ID",
      "password": true
    },
    {
      "type": "promptString",
      "id": "hedera-agent-key",
      "description": "HEDERA_AGENT_KEY",
      "password": true
    },
    {
      "type": "promptString",
      "id": "agent-allowed-tokens",
      "description": "AGENT_ALLOWED_TOKENS",
      "password": true
    }
  ],
  "servers": {
    "proctor": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "proctor-mcp"
      ],
      "env": {
        "PROCTOR_API": "${input:proctor-api}",
        "HEDERA_AGENT_ID": "${input:hedera-agent-id}",
        "HEDERA_AGENT_KEY": "${input:hedera-agent-key}",
        "AGENT_ALLOWED_TOKENS": "${input:agent-allowed-tokens}"
      }
    }
  }
}

VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs

proctor in other clients

proctor MCP server